No abstract

No abstract

Market-based task allocation mechanisms are designed to distribute a set of tasks fairly amongst a set of agents. Such mechanisms have been shown to be highly effective in simulation and when applied to multi-robot teams. Application of such mechanisms in real-world settings can present a range of practical challenges, such as knowing what is the best point in a complex process to allocate tasks and what information to consider in determining the allocation. The work presented here explores the application of market-based task allocation mechanisms to the problem of managing a heterogeneous human workforce to undertake activities associated with harvesting soft fruit. Soft fruit farms aim to maximise yield (the volume of fruit picked) while minimising labour time (and thus the cost of picking). Our work evaluates experimentally several different strategies for practical application of market-based mechanisms for allocating tasks to workers on soft fruit farms, identifying methods that appear best when simulated using a multi-agent model of farm activity.

With increasing demands for soft fruit and shortages of seasonal workers, farms are seeking innovative solutions for efficiently managing their workforce. The harvesting workforce is typically organised by farm managers who assign workers to the fields that are ready to be harvested. They aim to minimise staff time (and costs) and distribute work fairly, whilst still picking all ripe fruit within the fields that need to be harvested. This paper posits that this problem can be addressed using multi-criteria, multi-agent task allocation techniques. The work presented compares the application of Genetic Algorithms (GAs) vs auctionbased approaches to the challenge of assigning workers with various skill sets to fields with various estimated yields. These approaches are evaluated alongside a previously suggested method and the teams that were manually created by a farm manager during the 2021 harvesting season. Results indicate that the GA approach produces more efficient team allocations than the alternatives assessed.

By coupling a robot to a smart environment, the robot can sense state beyond the perception range of its onboard sensors and gain greater actuation capabilities. Nevertheless, incorporating the states and actions of Internet of Things (IoT) devices into the robot’s onboard planner increases the computational load, and thus can delay the execution of a task. Moreover, tasks may be frequently replanned due to the unanticipated actions of humans. Our framework aims to mitigate these inadequacies. In this paper, we propose a continual planning framework, which incorporates the sensing and actuation capabilities of IoT devices into a robot’s state estimation, task planing and task execution. The robot’s onboard task planner queries a cloud-based framework for actuators, capable of the actions the robot cannot execute. Once generated, the plan is sent to the cloud back-end, which will inform the robot if any IoT device reports a state change affecting its plan. Moreover, a Hierarchical Continual Planning in the Now approach was developed in which tasks are split-up into subtasks. To delay the planning of actions that will not be promptly executed, and thus to reduce the frequency of replanning, the first subtask is planned and executed before the subsequent subtask is. Only information relevant to the current (sub)task is provided to the task planner. We apply our framework to a smart home and office scenario in which the robot is tasked with carrying out a human’s requests. A prototype implementation in a smart home, and simulator-based evaluation results, are presented to demonstrate the effectiveness of our framework.